Noise-passing key system target confirmation method based on neural network

The invention discloses a key system target confirmation method for noise passing based on a neural network, and belongs to the field of automobile noise control. According to the method, a neural network model is trained through vehicle key structure parameters, vehicle key subsystem noise data and actual vehicle passing noise data, predicted passing noise is obtained, the predicted passing noise meets the national standard through adjustment of a subsystem target value, the finally determined subsystem target value is stored, and the vehicle passing noise is obtained. And product management and control are carried out as a subsystem target for managing and controlling the vehicle passing noise. According to the method, the problem that the passing noise is difficult to predict in the early stage of automobile development is solved, the key subsystem target of the vehicle passing noise is confirmed and controlled, the development period is shortened, and the cost is saved. 本发明公开了一种基于神经网络的通过噪声的关键系统目标确认方法，属于汽车